Abstract
ObjectiveThis study aimed to construct a radiomics-based MRI sequence from high-resolution magnetic resonance imaging (HRMRI), combined with clinical high-risk factors for non-invasive differentiation of the plaque of symptomatic patients from asyptomatic patients.MethodsA total of 115 patients were retrospectively recruited. HRMRI was performed, and patients were diagnosed with symptomatic plaques (SPs) and asymptomatic plaques (ASPs). Patients were randomly divided into training and test groups in the ratio of 7:3. T2WI was used for segmentation and extraction of the texture features. Max-Relevance and Min-Redundancy (mRMR) and least absolute shrinkage and selection operator (LASSO) were employed for the optimized model. Radscore was applied to construct a diagnostic model considering the T2WI texture features and patient demography to assess the power in differentiating SPs and ASPs.ResultsSPs and ASPs were seen in 75 and 40 patients, respectively. Thirty texture features were selected by mRMR, and LASSO identified a radscore of 16 radiomics features as being related to plaque vulnerability. The radscore, consisting of eight texture features, showed a better diagnostic performance than clinical information, both in the training (area under the curve [AUC], 0.923 vs. 0.713) and test groups (AUC, 0.989 vs. 0.735). The combination model of texture and clinical information had the best performance in assessing lesion vulnerability in both the training (AUC, 0.926) and test groups (AUC, 0.898).ConclusionThis study demonstrated that HRMRI texture features provide incremental value for carotid atherosclerotic risk assessment.
Highlights
Carotid atherosclerotic plaques contribute to ∼20% of the ischemic cerebrovascular events, including transient ischemic attack (TIA) [1]
Thirty texture features were selected by MaxRelevance and Min-Redundancy (mRMR), and least absolute shrinkage and selection operator (LASSO) identified a radscore of 16 radiomics features as being related to plaque vulnerability
This study demonstrated that high-resolution magnetic resonance imaging (HRMRI) texture features provide incremental value for carotid atherosclerotic risk assessment
Summary
Carotid atherosclerotic plaques contribute to ∼20% of the ischemic cerebrovascular events, including transient ischemic attack (TIA) [1]. Clinical trials have demonstrated that ultrasonography-defined luminal stenosis of ≥70% was predictive of future ischemic events in both symptomatic [2, 3] and asymptomatic [4, 5] patients. Doppler ultrasonography (CDUS), computed tomography angiography (CTA), contrast-enhanced magnetic resonance angiography (MRA), and high-resolution magnetic resonance imaging (HRMRI) have been used for non-invasive prediction of carotid plaque recently. Lower resolution and worse spatial resolution of the first-pass imaging of MRA are not suitable for predicting the structure of plaque. The acquisitions of non-isotropic voxels and lower matrix could result in partial volume effects that compromise carotid stenosis and plaque structure prediction [12]. Steady-state imaging of MRA has greater accuracy and higher resolution in depicting the structure of the plaque [10]. During the imaging of steady-state MRA, intravascular contrast agents could extend intravascular residence times with relatively increased cost. Further research is needed to explore the feasibility of a conventional contrast agent of MRA
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
